AMD Releases Orochi 2.0 With More CUDA/HIP Functions Implemented For Better Portability

[phoronix]

Phoronix: AMD Releases Orochi 2.0 With More CUDA/HIP Functions Implemented For Better Portability

AMD GPUOpen's Orochi project as a remidner is the effort for allowing dynamic runtime switching between the Radeon HIP and NVIDIA CUDA APIs to allow better cross-GPU portability. Today marks the availability of Orochi 2.0 for enhancing this API to target NVIDIA CUDA and AMD HIP hardware...

https://www.phoronix.com/news/AMD-Orochi-2.0-HIP-CUDA

[JEBjames]

@Michael

Typo

"AMD GPUOpen's Orochi project as a remidner is" should be "reminder"

[onlyLinuxLuvUBack]

@Michael

Typo

"AMD GPUOpen's Orochi project as a remidner is" should be "reminder"

dwibly dictionary:

remidner noun

re . mid. ner


A middle man solution.

[NeoMorpheus]

Ngreedia white knights assemble!

lol

[timofonic]

Crap instead proper GPU computing ecosystem.

Make OpenCL great again or make Vulkan Computing surpass it. And make ZLUDA a first priority project such as in DXVK. Get an army of lawyers and AMD will surpass NVIDIA.

[byteabit]

So this is API routing? Like what WINE does for the Windows API.

[Eirikr1848]

Is this similar to ZLUDA in any way shape or form - just distributed?

[Svyatko]

Is this similar to ZLUDA in any way shape or form - just distributed?

No. Code generation vs. running a code.